Open
Conversation
Fetch all EIPs from the ethereum/EIPs GitHub repo via tarball download, parse YAML frontmatter + full markdown body, and build a semantic search index using the existing MiniLM-L6-v2 embedding model. Key features: - Bulk fetch via GitHub tarball API (single request for all ~900 EIPs) - Local cache with commit SHA tracking for incremental updates - Per-chunk vector caching with SHA256 text hashes (skip re-embedding unchanged content) - Content chunking at 600-char paragraph boundaries for the 512-token model - Strips code blocks, URLs, tables, and dense hex before embedding - Hybrid scoring: semantic similarity + exact text match boost (queries > 4 chars) - Multi-chunk deduplication in search results (best score per EIP) - MCP tool (search_eips) and CLI command (ep search eips) - Filter by status, category, and type - Non-fatal initialization (gracefully disabled if GitHub unreachable) - BuildSearchOnly app mode for CLI search (no proxy/sandbox needed)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
search_eipsMCP tool andep search eipsCLI commandethereum/EIPsGitHub repo via tarball API (single request), parses YAML frontmatter + full markdown bodyBuildSearchOnlyapp mode so CLI search commands don't require proxy/sandboxNew packages
pkg/types/eip.go—EIPstruct andEIPVectorcache typepkg/eips/— fetcher (GitHub tarball), parser (YAML frontmatter), registry (cache lifecycle + commit SHA tracking)pkg/resource/eip_index.go— chunking, stripping, embedding, hybrid searchpkg/tool/search_eips.go— MCP tool with status/category/type filtersTest plan
pkg/eips/parser_test.go— unit tests for YAML frontmatter parsing (5 cases)pkg/eips/integration_test.go— fetch from GitHub, cache round-trip, vector persistencepkg/resource/eip_index_test.go— full search integration test, vector reuse testmake lint— 0 issuesmake test— all passingep search eips "63/64 rule","account abstraction","blob transactions","proof of stake"